Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21588
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas, indicating list-like structures or complex sentence formulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaz
    -0.69
    uce
    -0.67
    enz
    -0.64
    aughter
    -0.63
    eni
    -0.62
    ratulations
    -0.62
     Cros
    -0.61
    uru
    -0.60
    chin
    -0.60
    iless
    -0.59
    POSITIVE LOGITS
     namely
    1.53
     whereby
    1.22
     albeit
    1.20
     which
    1.09
     insofar
    1.06
     wherein
    1.06
     viz
    1.01
    which
    0.98
     rather
    0.96
     whereas
    0.95
    Activations Density 0.392%

    No Known Activations